Nougat_base_JHR_fewshot

bustamiyusoef/Nougat_base_JHR_fewshot

Nougat_base_JHR_fewshot is a image-text-to-text model from bustamiyusoef. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as cc-by-nc-4.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

19% of all-time downloads

All-time downloads

Public

Parameters

349M

698 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors698 MB · 99%

Parameter types

How the weights are stored.

BF16349M · 100%

Try a prompt

Base models

facebook/nougat-base

Model card

From the Hugging Face model README

Nougat_base_JHR_fewshot

This model is a fine-tuned version of facebook/nougat-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 3.2931

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 1
eval_batch_size: 1
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	5	3.0135
3.3244	2.0	10	2.8585
3.3244	3.0	15	2.7424
2.4873	4.0	20	2.7462
2.4873	5.0	25	2.6942
2.095	6.0	30	2.9536
2.095	7.0	35	3.2083
1.7465	8.0	40	3.0990
1.7465	9.0	45	3.1203
1.5195	10.0	50	3.2931

Framework versions

Transformers 4.47.1
Pytorch 2.5.1+cu121
Datasets 4.0.0
Tokenizers 0.21.0

Task: Image-Text-to-Text
Library: transformers
Type: vision-encoder-decoder
License: cc-by-nc-4.0
Created: Aug 12, 2025
Updated: Aug 12, 2025